• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.605-616
• /
• 2000

Three primary interests frequently raised by mortgage companies are introduced and the corresponding statistical approaches for the default probability in mortgage companies are examined. Statistical models considered in this paper are time series, logistic regression, decision tree, neural network, and discrete time models. Usage of the models is illustrated using an artificially modified data set and the corresponding models are evaluated in appropriate manners.

• Economic and Environmental Geology
• /
• v.40 no.1 s.182
• /
• pp.115-128
• /
• 2007

This study proposed a modified logistic regression model for a probabilistic prediction of debris flow on natural terrain at the granitic rock area. The modified model dose not contain any categorical factors that were used in the previous model and secured higher reliability of prediction than that of the previous one. The modified model is composed of lithology, two factors of geomorphology, and three factors of soil property. Verification result shows that the prediction reliability is more than 86%. Using the modified regression model, the landslide prediction maps were established. In case of Sacheon area, the prediction map showed that the landslide occurrence was not well corresponded with the model since, even though the forest-fred area was distributed on the center of the model, no factors were considered for the landslide predictions. On the other hand, the prediction model was well corresponded with landslide occurrence at Jumunjin-Yeongok area. The prediction model developed in this study has very high availability to employ in other granitic areas.

• Journal of Korean Academy of Nursing
• /
• v.44 no.2
• /
• pp.219-227
• /
• 2014

Purpose: To assess whether the Modified Early Warning Score (MEWS) predicts the need for intensive care unit (ICU) transfer for patients with severe sepsis or septic shock admitted to general wards. Methods: A retrospective chart review of 100 general ward patients with severe sepsis or septic shock was implemented. Clinical information and MEWS according to point of time between ICU group and general ward group were reviewed. Data were analyzed using multivariate logistic regression and the area under the receiver operating characteristic curves with SPSS/WIN 18.0 program. Results: Thirty-eight ICU patients and sixty-two general ward patients were included. In multivariate logistic regression, MEWS (odds ratio [OR] 2.02, 95% confidence interval [CI] 1.43-2.85), lactic acid (OR 1.83, 95% CI 1.22-2.73) and diastolic blood pressure (OR 0.89, 95% CI 0.80-1.00) were predictive of ICU transfer. The sensitivity and the specificity of MEWS used with cut-off value of six were 89.5% and 67.7% for ICU transfer. Conclusion: MEWS is an effective predictor of ICU transfer. A clinical algorithm could be created to respond to high MEWS and intervene with appropriate changes in clinical management.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.787-795
• /
• 2009

This paper presents a histogram equalization based on the logistic function for enhancing the quality of images. The histogram equalization is a simple and effective spatial processing method that it enhances the quality by adjusting the brightness of image. The logistic function that is a nonlinear transformation function is applied to adaptively enhance the brightness of the image according to its intensity level frequency. We propose a flexible and asymmetrical logistic function by only using the intensity level with maximum frequency and the maximum intensity level in an histogram, and the total number of pixels. The proposed function excludes both the computation load of an exponential function and the heuristic setting of an optimal parameter values in the traditional logistic function. The proposed method has been applied for equalizing many images with a different resolution and histogram distribution. The experimental results show that the proposed method has the superior enhancement performances and the faster equalizing speed compared with the traditional histogram equalization and the adaptively modified histogram equalization, respectively. And the proposed histogram equalization can be used in various multimedia systems in real-time.

• Journal of Korean Biological Nursing Science
• /
• v.16 no.4
• /
• pp.259-266
• /
• 2014

Purpose: The purpose of this study was to analyze risk factors in predicting medical patients transferred to Intensive Care Unit (ICU) on the general ward. Methods: We reviewed retrospectively clinical data of 120 medical patients on the general ward and a Modified Early Warning Score (MEWS) between ICU group and general ward group. Data were analyzed with multivariate logistic regression and the area under the receiver operating characteristic curves using SPSS/WIN 18.0 program. Results: Fifty-two ICU patients and 68 general ward patients were included. In multivariate logistic regression, the MEWSs (Odds Ratio [OR], 1.91; 95% confidence interval [CI], 1.32-2.76), sequential organ failure assessment score (OR, 1.28; 95% CI, 1.10-1.72), $PaO_2/FiO_2$ ratio (OR, 0.98; 95% CI, 0.98-0.99), and saturation (OR, 0.93; 95% CI, 0.88-0.99) were predictive of ICU transfer. The sensitivity and the specificity of the MEWSs used with a cut-off value of six were 80.8% and 70.6% respectively for ICU transfer. Conclusion: These findings suggest that early prediction and treatment of patients with high risk of ICU transfer may improve the prognosis of patients.

• Journal of Forest and Environmental Science
• /
• v.30 no.2
• /
• pp.201-207
• /
• 2014

This study was conducted to estimate the best-fit nonlinear height-DBH growth models for Larix kaempferi in Gangwon and North Gyeongsang province in South Korea. Exponential, Modified Logistic, Chapman-Richards, and Weibull function were used for estimating height-DBH models. To evaluate the selected models, $R^2$, RMSE, MD, MAD, and residual plots were performed in each model. Also, the coefficients and patterns in models of the previous studies were compared with those in this study. The result showed that Weibull equation was found to be the best-fit model with $R^2$=0.9837, RMSE=2.6133, MD=0.0089, and MAD=2.0896. All model parameters in our study had similar values to those in the previous models except for asymptotic parameter a. Our research result showed that Gangwon and North Gyeongsang province were superior to other provinces with regard to height growth for Larix kaempferi.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.8
• /
• pp.289-296
• /
• 2020

The study investigates the association between the effectiveness of the board of directors and the likelihood that a company receives a modified audit opinion (as a measure of the quality of companies' external financial reporting) in Malaysia. The sample companies were extracted from the population of publicly-available information mainly the annual reports of publicly-listed companies on the Bursa Malaysia. 136 firm-year observations listed on Bursa Malaysia were identified to examine the relationship between the effectiveness of the board of directors and a modified audit opinion. Data used in this study are collected from two separate sources - annual reports and Datastream. Any missing financial figure from Datastream was acquired from the annual reports. To test the study's hypotheses, we use the pooled cross-sectional logistic regression analysis for 136 firm-year observations listed on Bursa Malaysia over the period 2009-2011. The evidence we have uncovered is consistent with the hypothesis that companies with large score of the board of directors' effectiveness are less possible to receive a modified audit opinion. Therefore, the result confirms that the combined effect of the board of directors' characteristics has a significant negative association with the likelihood of the companies receiving a modified audit opinion.

• Korean Journal of Psychosomatic Medicine
• /
• v.25 no.1
• /
• pp.56-62
• /
• 2017

Objectives : The objective of this study was to investigate the relationship between psychological distress and pain in cancer patients. Methods : 249 patients with cancer who visited National Health Insurance Service Ilsan Hospital between April 2013 and March 2014 were evaluated with National Cancer Center Psychological Symptom Inventory(NCC-PSI) which consisted of Modified Distress Thermometer(MDT) and Modified Impact Thermometer(MIT). Each scale was divided into 3 subscales targeting separate symptoms: insomnia, anxiety, and depression. Psychological distress was defined as positive for those who scored above the cutoff values in at least one of all six subscales. The Numeric Rating Scale for Pain(NRS-Pain) was used to assess the subjective severity of pain. Logistic regression was performed to investigate the association between psychological distress and pain. Results : Univariate logistic regression analysis showed that pain, gender, compliance, and two subscale scores of Hospital Anxiety and Depression Scale(HADS) were significantly associated with psychological distress. Multivariate logistic regression analysis showed that pain and HADS anxiety subscale score maintained a statistically significant association with psychological distress adjusted for variables including age, gender, years of education, Eastern Cooperative Oncology Group performance status, cancer stage, Charlson Comorbidity Index, compliance, and HADS depression subscale score. One point increase in pain was 1.31 times more likely to cause psychological distress. In secondary analysis, pain was significantly associated with all subscales of NCC-PSI, except MIT-anxiety subscale. Conclusions : This study suggests that NCC-PSI, a screening tool for psychological distress, reflects pain. We recommend that physicians who treat cancer patients consider the examination of psychological distress which provides comprehensive evaluation of various factors regarding quality of life.

• Physical Therapy Korea
• /
• v.14 no.3
• /
• pp.81-89
• /
• 2007

The purpose of this study was to utilize the K-MBI (Korean Modified Barthel Index) and subscales of K-MBI in predicting the length of hospital stay (LOS) and the discharge destinations for stroke patients. The study population consisted of 97 stroke patients (57 men and 40 women) admitted to the Seoul National University at the Bundang Hospital. All participants were assessed by K-MBI at admission and discharge after rehabilitation therapy and the information available was investigated at admission. The data were analyzed by using the Mann-Whitney U test, the stepwise multiple regression and the logistic regression. The median LOS was 30 days (mean, 32.8 days; range, 22 to 43 days). The K-MBI score at initiation of rehabilitation therapy (p<.001), the type of stroke and living habits before a stroke were the main explanatory indicators for LOS (p<.05). Within the parameters of K-MBI measured at initiation for rehabilitation, feeding and chair/bed transfer were the explanatory factors for LOS prediction (p<.01). Confidence in the prediction of LOS was 20%. Significant predictors of discharge destination in a logistic regression model were the discharge K-MBI score, sex and hemiplegic side. Dressing in items of discharge K-MBI was the significant predictor of discharge destination. The K-MBI score was the most important factor to predict LOS and discharge destination. Knowledge of these predictors can contribute to more appropriate treatment and discharge planning.

• Health Policy and Management
• /
• v.4 no.2
• /
• pp.58-76
• /
• 1994

In order to study factors affecting the use of the ambulatory physician services. Andersen's model for health utilization was modified by adding the health behavior component and examined with three different approaches. Three different approaches were the multiople regression model, logistic regression model, and LISREL model. For multiple regression, dependent variable was reported illness-related visits to a physician during past one year and independent variables are variaous variables measuring predisposing factor, enabling factor, need factor and health behavior. For the logistic regression, dependent variable was visit or no-visit to a physician during past one year and independent variables were same as the multiple regression analysis. For the LISREL, five endogenous variables of health utiliztion, predisposing factor, enabling factor, need factor, and health behavior and 20 exogeneous variables which measures five endogenous variables were used. According to the multiple regression analysis, chronic illness, health status, perceived health status of the need factor; residence, sex, age, marital status, education of the predisposing factor ; health insurance, usual source for medical care of enabling factor were the siginificant exploratory variables for the health utilization. Out of the logistic regression analysis, health status, chronic illness, residence, marital status, education, drinking, use of health aid were found to be significant exploratory variables. From LISREL, need factor affect utilization most following by predisposing factor, enabling factor and health behavior. For LISREL model, age, education, and residence for predisposing factor; health status, chronic illess, and perceived health status for need factor; medical insurance for enabling factor; and doing any kind of health behavior for the health behavior were found as the significant observed variables for each theoretical variables.